{"total":31,"rows":[{"id":"2406.01574","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","created":"2024-06-03","cited_by_count":1848,"area":null},{"id":"2410.01679","title":"VinePPO: Refining Credit Assignment in RL Training of LLMs","created":"2024-10-02","cited_by_count":183,"area":null},{"id":"2508.15761","title":"Waver: Wave Your Way to Lifelike Video Generation","created":"2025-08-21","cited_by_count":52,"area":null},{"id":"2509.16679","title":"Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle","created":"2025-09-20","cited_by_count":35,"area":null},{"id":"2502.18008","title":"NotaGen: Advancing Musicality in Symbolic Music Generation with Large Language Model Training Paradigms","created":"2025-02-25","cited_by_count":30,"area":null},{"id":"2410.12864","title":"Investigating Implicit Bias in Large Language Models: A Large-Scale Study of Over 50 LLMs","created":"2024-10-13","cited_by_count":25,"area":null},{"id":"2510.14807","title":"Beyond the Sampled Token: Preserving Candidate Support in RLVR","created":"2025-10-16","cited_by_count":18,"area":null},{"id":"2410.09347","title":"Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment","created":"2024-10-12","cited_by_count":14,"area":null},{"id":"2506.03483","title":"APT: Improving Specialist LLM Performance with Weakness Case Acquisition and Iterative Preference Training","created":"2025-06-04","cited_by_count":12,"area":null},{"id":"2404.19296","title":"Octopus v4: Graph of language models","created":"2024-04-30","cited_by_count":11,"area":null},{"id":"2406.17969","title":"Encourage or Inhibit Monosemanticity? Revisit Monosemanticity from a Feature Decorrelation Perspective","created":"2024-06-25","cited_by_count":10,"area":null},{"id":"2602.08682","title":"ALIVE: Animate Your World with Lifelike Audio-Video Generation","created":"2026-02-09","cited_by_count":9,"area":null},{"id":"2412.04167","title":"Bench-CoE: a Framework for Collaboration of Experts from Benchmark","created":"2024-12-05","cited_by_count":7,"area":null},{"id":"2508.06482","title":"Post-training for Efficient Communication via Convention Formation","created":"2025-08-08","cited_by_count":7,"area":null},{"id":"2411.05199","title":"CodeLutra: Boosting LLM Code Generation via Preference-Guided Refinement","created":"2024-11-07","cited_by_count":6,"area":null},{"id":"2502.13794","title":"LESA: Learnable LLM Layer Scaling-Up","created":"2025-02-19","cited_by_count":5,"area":null},{"id":"2506.03028","title":"Protein Inverse Folding From Structure Feedback","created":"2025-06-03","cited_by_count":5,"area":null},{"id":"2604.01597","title":"Learning from the Right Rollouts: Data Attribution for PPO-based LLM Post-Training","created":"2026-04-02","cited_by_count":4,"area":null},{"id":"2505.15353","title":"Establishing a Scale for Kullback-Leibler Divergence in Language Models Across Various Settings","created":"2025-05-21","cited_by_count":3,"area":null},{"id":"2605.08666","title":"The Cancellation Hypothesis in Critic-Free RL: From Outcome Rewards to Token Credits","created":"2026-05-09","cited_by_count":3,"area":null},{"id":"2404.07611","title":"NoticIA: A Clickbait Article Summarization Dataset in Spanish","created":"2024-04-11","cited_by_count":2,"area":null},{"id":"2505.02410","title":"Bielik 11B v2 Technical Report","created":"2025-05-05","cited_by_count":2,"area":null},{"id":"2603.05776","title":"PVminerLLM: Structured Extraction of Patient Voice from Patient-Generated Text using Large Language Models","created":"2026-03-06","cited_by_count":2,"area":null},{"id":"2408.04658","title":"Winning Amazon KDD Cup'24","created":"2024-08-05","cited_by_count":1,"area":null},{"id":"2506.08616","title":"Generalizing while preserving monotonicity in comparison-based preference learning models","created":"2025-06-10","cited_by_count":1,"area":null},{"id":"2604.10799","title":"Advancing Polish Language Modeling through Tokenizer Optimization in the Bielik v3 7B and 11B Series","created":"2026-04-12","cited_by_count":1,"area":null},{"id":"2412.09280","title":"Learning to Solve Domain-Specific Calculation Problems with Knowledge-Intensive Programs Generator","created":"2024-12-12","cited_by_count":0,"area":null},{"id":"2501.00562","title":"An Overview and Discussion on Using Large Language Models for Implementation Generation of Solutions to Open-Ended Problems","created":"2024-12-31","cited_by_count":0,"area":null},{"id":"2509.04442","title":"Delta Activations: A Representation for Finetuned Large Language Models","created":"2025-09-04","cited_by_count":0,"area":null},{"id":"2604.24536","title":"Generating Place-Based Compromises Between Two Points of View","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2607.20057","title":"Antigen-specific Antibody Multi-modal Foundation Model for Functional Antibody Design","created":"2026-07-22","cited_by_count":0,"area":null}],"next_cursor":null}